The API will help developers integrate the company’s technology into their apps.
“Developers can now integrate DALL-E directly into their apps and products through our API”, the company said. “They can start building with the technology in a matter of minutes.”
DALL-E is currently available as a standalone commercial service. “More than three million people are already using DALL-E to extend their creativity and speed up their workflows”, OpenAI boasted, saying their userbase is already “generating over four million images a day”.
The API allows people to generate novel 1024×1024 images from text descriptions called “prompts”. The generated images can vary in style from photorealistic to abstract, and many styles in between. DALL-E “excels at following natural language descriptions”, they say. “Users can plainly describe what they want to see.”
In order to use the API, developers need to register with OpenAI and get a private API key that allows access to the DALL-E generator. OpenAI levies a fee for each image generated. The fee structure is based on image resolution. Images that are 1024×1024 cost $0.02 an image, 512×512 images cost $0.018 per image, and 256×256 images cost $0.016 per image.
Integrating with Microsoft, CALA and others
Microsoft is also integrating DALL-E in Bing and Microsoft Edge with Image Creator, allowing users to create images if web results don’t return what they’re looking for.
CALA, “the world’s first fashion and lifestyle operating system”, uses DALL-E in its artificial intelligence tools to allow users to generate new design ideas from natural text descriptions or uploaded reference images.
Mixtiles, a fast-growing photo startup, uses the DALL-E API to create and frame emotionally resonating artwork by guiding users through a creative process.